GuardReasoner: Towards Reasoning-based LLM Safeguards
Paper
•
2501.18492
•
Published
•
89
AI censorship
-
-
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Paper • 2412.19512 • Published • 8 -
Course-Correction: Safety Alignment Using Synthetic Preferences
Paper • 2407.16637 • Published • 27 -
Refusal in Language Models Is Mediated by a Single Direction
Paper • 2406.11717 • Published • 3 -
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Paper • 2505.11049 • Published • 61 -
Lifelong Safety Alignment for Language Models
Paper • 2505.20259 • Published • 24 -
Automating Steering for Safe Multimodal Large Language Models
Paper • 2507.13255 • Published • 3 -
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
Paper • 2507.11097 • Published • 63 -
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
Paper • 2407.05965 • Published -
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report
Paper • 2507.16534 • Published • 6 -
AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
Paper • 2508.02079 • Published • 2 -
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper • 2508.06601 • Published • 6